- class torch.nn.PairwiseDistance(p=2.0, eps=1e-06, keepdim=False)¶
Computes the pairwise distance between input vectors, or between columns of input matrices.
Distances are computed using
p-norm, with constant
epsadded to avoid division by zero if
pis negative, i.e.:
where is the vector of ones and the
p-norm is given by.
Input1: or where N = batch dimension and D = vector dimension
Input2: or , same shape as the Input1
Output: or based on input dimension. If
True, then or based on input dimension.
>>> pdist = nn.PairwiseDistance(p=2) >>> input1 = torch.randn(100, 128) >>> input2 = torch.randn(100, 128) >>> output = pdist(input1, input2)